Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents hundreds of hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, feel free to ⚡tip 😉
LC123 nodes: https://github.com/lonecatone23/ComfyUI_LC123_nodes
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules.
This is an advanced workflow. I encourage you to take the time to learn it. If you feel overwhelmed, you can start here:
https://civarchive.com/models/2348914/zimage-base-and-turbo-essentials-workflow
A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown
也有中文说明
V15
This brings the workflow inline with my latest sigma and post processing updates
better sigmas
better Aspect ratio control
better post processing
standalone upscalers
less node packs
V13.2
You need to update the node pack
Change to Color match
Change to LC Sharpen Pro
Change to Lut
Lut folder now auto downloads
Other tweaks
Updated Notes
Introducing LC123 Nodes
These nodes are BETA. If you do not like them, simply delete it and paste the old pack back in. You will only need to change the "Org pic" name on the getnode for the color correct. Also, please provide me feedback so I can adjust.
VRAM settings can be adjusted in the ComfyUI Settings menu:
Smart Denoise (LCImageDenoise)
Removes noise while trying to keep detail
Color Match (LCColorMatch)
Matches colors to a reference image (usually Image 2)
Bloom (LCBloom)
Soft glow on bright areas (camera light bloom)
Vignette (LCVignette)
Darkens (or lightens) the edges
Image RGB (LCImageRGB)
Simple red / green / blue channel gain
Lift / Gamma / Gain (LCLiftGammaGain)
Classic three-way color corrector
Auto White Balance (LCAutoWhiteBalance)
Tries to neutralize overall color cast
Vibrance (LCVibrance)
Boosts muted colors without destroying already-saturated areas
Chromatic Aberration (LCChromaticAberration)
Shifts RGB channels for a 3-D / vintage lens look
Sharpen Pro (LCSharpenPro)
Adaptive mid-tone contrast / micro-contrast
Image Adjust (LCImageAdjust)
Brightness, Contrast, Saturation, Sharpness, Blur
Lens FX (LCLensFX)
General lens distortion and optical effects
Lens Profile (LCLensProfile)
Applies real lens characteristics (e.g. Canon 50mm f/1.8)
Film Stock B&W (LCFilmStockBW)
Converts to black & white using real film responses
Film Stock Color (LCFilmStockColor)
Applies classic color film response (Ektachrome, Portra, etc.)
Film Grain (LCFilmGrain)
Realistic film grain with lots of control
Desaturate (LCImageDesaturate)
Partial or full desaturation.
Apply LUT (LCApplyLUT)
Applies a 3D LUT (.cube file)
Image Crop (LCImageCrop)
Inline crop tool
Text Overlay (LCTextOverlay)
Adds text on the final image
LC Watermark 💧(LCWatermark)
dynamically adds any image as a watermark
Plus plenty of other options. Check them out here: https://github.com/lonecatone23/ComfyUI_LC123_nodes
V10.0
Upgraded Samplers to Clownshark Samplers
Added a Denoise Slider
Added the ability to color correct to the orgiginal image without having to load it again
minor additions
V9.0
Because it is not in my nature to leave things alone....
Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better results both SFW &NSFW
Updated links to teh latest detailers for all
Controlnet Update.
Added local bypass nodes so ou don't have to zoom and scroll
Added a quality modifier prompt area that follows after Qwen so that they stay preserved.
Major update to notes, especially for detailers
Ver 6.0
Overhauled the detailers
Body detailers are better calibrated
Face. eyes, and hands are now run by Z-Image for better consistency
Please give me feedback with any issues on this, especailly RAM related.
added a LoRA area for character and detail LoRAs
Changed the save area:
You can choose to embed the workflow or not
You can add a simple date to the metadata folder for better organization
Changed the prompt area:
added a sentence remover that helps eliminate unwated words (CivitAI flags 🚩)
Added an inline crop tool in the post processing Suite
Minor correction to the gguf area to deal with the quantized DIT models crashing.
Added better notes.
Ver 5.0
Added Face Swap
Added a sentence remover to prevent CivitAI flags
Improved detailers
Fixedbroken metadata saver from ComfyUi
Ver 4.0
I did a massive overhaul to catch it up to the new nodes and ComfyUi updates that broke a lot of stuff.
Upgraded The Controlnet and prompt assist area
Added a sampler swap to make it easier to go from Base to Turbo wityhout having to reset everything.
Major overhaul of the detailer area (see release notes)
Major overhaul of the post production Suite to focus on realism/ camera
All in 1 workflow:
Controlnet
Lora Loader
Advanced KSampler
Seed variance enhancer
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, eyes, and expressions
⛔ NSFW anatomy correctors (Male and Female)
Anime detailer
Seed VR2 Upscaler to get 4k on low VRAM
Massive Post Production Suite
也有中文说明
All images were created using the standard FP16 version with no loras (except for a character one). For even better quality, use this Lora with it: https://civarchive.com/models/2206377/zit-mystic-xxx
Check out my other models:
Original Version (SFW): https://civarchive.com/models/2184844/zit-workflow-with-prompt-assist-controlnet-lora-loaders-inpainting-upscaler-detailers-expression-control-and-post-processing-i2i-t2i
For ultimate Anime detail and control: https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations
For Realism and variety over the base model: https://civarchive.com/models/2231181/z-image-ultra-real-workflow
Description
added a checkpoint option.
FAQ
Comments (27)
According to the description, it’s very cool, it’s clear that a lot of work has been done. thank you very much for such work. such an abundance of nodes is a little scary, I hope my 3070 can handle it
I purposely set it up to run on 6-8gb. Nodes are not the issue. I suggest you read the instructions before using it as you'll have to adjust some settings, but it should work.
Cool_Natural_Breeze.cube not available in the luts folder
you can download it. The instructions are in the notes. Go here. There are tons of free options:
https://freshluts.com/
@lonecatone23 I have already searched there, this lut is not available there.
@torc007689 those are there for examples. You don't necessarily need to use a specific one.
Its im the Illutstrious update i did ladt night. I'll probably be updating this model on the next day or so, but since nobody who uses it has tipped me, its not my priority
hey man, great work! how does the inpaint work?
ok nevermind, saw the other comment.
Question, only looking for a good inpaint tool.
Let's say I have a generated photo of my character that I like most, I am trying to change only:
face expression, body pose, where the character is looking (direction), text on clothes/environment/ background/ minor stuff in the background, all while keeping the character looking consistent with the initial image/generation inserted into inpaint.
Basically keeping the whole photo composition for the most part, and only changing a few minor things I mentioned. I have a lora of my character as well if that helps
note: the things I want inpainted wouldn't necessarily be inpainted all at the same time/one go, depending on what things I like and dislike in my initial photo I want inpaint on. Was just sharing what abilities I would like for it to have
Can I ask how much VRAM will this workflow need?
very little. I can run it on an 8gb graphics card. I have it set up for optimization. You may want to try the essentials workflow first and see how that goes before committing to this one.
@lonecatone23 thanks for the response. I will definitely try it
by any chance, is there any video tutorial for this?
No, but I have a very detailed tutorial https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown-and-troubleshooting-guide
thank you so much, I am using your guide & your workflow in chatgpt to learn in depth. your works are really amazing and interesting. waiting to see the result after I learn...
@atofael10434 I at some point am goig to start a tutorial set of videos for Comfy Workflow building.
It may be easier to start on one of my essentials workflows. They are all purposely similar so that you can advance to the Pro ones. This one is super intimidating
module missing: sage attention
Do you have Sage attention on your computer? It's teh red node dead center
I'm a beginner. I'm also a little under the weather. Anyway I somehow missed "this is an advanced workflow" and now I've installed it. It installed a whole bunch of nodes and stuff. The workflow is huge and unfamiliar. I feel like a moron.
Noooo. It's actuallly quite easy. If you have all the nodes installed use it. I have a manual for it.
Just turn off evrything but "save draft" and start messing around with it. You can't break it.
Also, all the nodes are the same, so you coudl download the essentials version and start there, then advance.
Thanks for the encouragement. I'm still trying to figure out what prompts work and which don't. Keeping it simple. I'll definitely get around to using this in the future. It looks cool.
@potatometer350 use the prompt assist feature. let it write it for you, then learn from there
Hi I'm a newbie.. Anytime I try to create an image including the control net I get an image of just static. I've spent a whole day trying to get this to work with Turbo and it just doesn't. I feel like I have the wrong models and the tutorial provided doesn't cover that well.
That's weird. This one is really stable.
Make sure youa re using the following;
Z-image-turbo-fun-controlnet-union 2.0
Z_image turbo (not someone else model. Start with that) with weight d type set to default
qwen_3_4b text encoder with lumina2 as they type
In the aio preporcessor, use CannyEdge preprocessor or DepthANything preprocessor
In teh box that says controplnet, make sure the value is set to 0.80
9 steps
cfg 1.0
euler
simple
These are the most basic settings. If that does not work, you can message me directly
I figured it out.. I was mixing Zimage-turbo patch with regular z-image diffuser. I got used to filling the models based on how things were labeled in workflows I didn't realize it worked differently for Zimage or that Zimage is just a diffuser. Thanks for the response!
@Hartlezoro You're welcome! Hopefully you like the workflow!